© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209150
    Prev
    Next
    INDEX
    Explanations

    company suffixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     doing
    1.88
     DBA
    1.79
    Doing
    1.70
     Doing
    1.66
    doing
    1.62
     d
    1.55
    DB
    1.29
     trading
    1.29
    dba
    1.27
     DB
    1.26
    POSITIVE LOGITS
     vattati
    0.38
    어서
    0.34
    奉
    0.34
    萛
    0.34
    ktir
    0.33
     anam
    0.33
    regression
    0.33
    춧
    0.33
    меч
    0.32
    tunnel
    0.32
    Activations Density 0.003%

    No Known Activations